论文/arXiv 2608.19574·2 个月前

HiTac-WAM：用于富接触机器人操作的分层触觉世界动作模型

针对现有触觉世界动作模型未分层建模物理依赖，HiTac-WAM分解预测触觉状态并用于规划，在三项真机操作中验证。

AI 整理

• 数据与采集

原文链接：HiTac-WAM: A Hierarchical Tactile World Action Model for Contact-Rich Robot Manipulation（arXiv 2608.19574 · 发布日期：2026-08-20）

HiTac-WAM: A Hierarchical Tactile World Action Model for Contact-Rich Robot Manipulation

针对现有触觉世界动作模型未分层建模物理依赖，HiTac-WAM分解预测触觉状态并用于规划，在三项真机操作中验证。

核心要点

• 现有触觉感知模型多将未来触觉表示为图像或潜变量，缺少对触觉层级物理依赖的建模。
• HiTac-WAM在执行前为候选动作块预测接触状态、3D形变场和滑移风险的层级触觉序列。
• 模型用定向注意力隔离触觉查询，并据触觉预测与任务进度排序候选动作、触发纠正性重规划。
• 实验中接触F1均值达0.921，并在三项真机任务中将平均成功率从31.1%提升至72.2%。

验证范围与局限：验证范围为芯片抓取、黑板擦除和USB插入三项真机操作任务。

英文摘要 (Abstract)

World action models jointly predict future visual observations and actions, whereas existing tactile-aware variants typically represent future touch as an image or latent stream without modeling the physical dependencies that organize tactile states hierarchically. We present HiTac-WAM, a hierarchical tactile world action model that forecasts a sequence of future tactile states for each candidate action chunk before execution. The forecast factorizes into contact state, a 3D deformation field, and slip risk, organized as a directed hierarchy in which each downstream stage is conditioned on stop-gradient signals from preceding stages. A directed attention mask allows tactile queries to attend to the video-action context of each candidate while preventing video and action queries from attending to tactile tokens. For planning, HiTac-WAM ranks candidate action chunks using tactile forecasts and task-progress estimates. For execution, the selected tactile forecast is retained as a reference; persistent discrepancies between predicted and observed tactile states trigger corrective replanning. HiTac-WAM achieves a mean contact F1 of 0.921; under matched training budgets, the directed hierarchy reduces 3D displacement L2 error by 17.6% relative to the deformation-only predictor and improves slip AUPRC by 60.4% relative to the slip-only predictor. Across chip grasping, blackboard erasing, and USB insertion, selection guided by the hierarchical forecasts increases the average real-robot success rate from 31.1% to 61.1%, while the full system attains 72.2%.

作者：Chao Xue, Chaofan Zhang, Wenxuan Ma, Guocai Yao, Shaowei Cui, Shuo Wang

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2608.19574：HiTac-WAM: A Hierarchical Tactile World Action Model for Contact-Rich Robot Manipulation访问 2026-10-21